Dunedin Hospital Eye Department, Dunedin, New Zealand.
University of Otago, Dunedin, New Zealand.
Clin Exp Ophthalmol. 2019 May;47(4):484-489. doi: 10.1111/ceo.13433. Epub 2018 Nov 15.
Artificial intelligence (AI) algorithms are under development for use in diabetic retinopathy photo screening pathways. To be clinically acceptable, such systems must also be able to classify other fundus abnormalities and clinical features at the point of care.
We aimed to develop an AI system that can detect several fundus pathologies and report relevant clinical features.
Convolutional neural network training with retrospective data set.
Colour fundus photos were obtained from publicly available fundus image databases.
Images were uploaded to a web-based AI platform for training and validation of AI classifiers. Separate classifiers were created for each fundus pathology and clinical feature.
Accuracy, sensitivity, specificity and area under receiver operating characteristic curve (AUC) for each classifier.
We obtained 4435 images from publicly available fundus image databases. AI classifiers were developed for each disease state above. Although statistical performance was limited by the small sample size, average accuracy was 89%, average sensitivity was 75%, average specificity was 89% and average AUC was 0.58.
This study is a proof-of-concept AI system that could be implemented within a diabetic photo-screening pathway. Performance was promising but not yet at the level that would be required for clinical application. We have shown that it is possible for clinicians to develop AI classifiers with no previous programming or AI knowledge, using standard laptop computers.
人工智能 (AI) 算法正在开发中，用于糖尿病视网膜病变的照片筛查途径。为了在临床上可以接受，这样的系统还必须能够在护理点对其他眼底异常和临床特征进行分类。
我们旨在开发一种能够检测几种眼底病变并报告相关临床特征的人工智能系统。
使用回顾性数据集进行卷积神经网络训练。
彩色眼底照片来自公开的眼底图像数据库。
将图像上传到基于网络的人工智能平台，用于训练和验证人工智能分类器。为每种眼底病变和临床特征创建单独的分类器。
每个分类器的准确性、敏感度、特异性和接收者操作特征曲线下的面积 (AUC)。
我们从公开的眼底图像数据库中获得了 4435 张图像。为每个疾病状态开发了 AI 分类器。虽然统计性能受到样本量小的限制，但平均准确率为 89%，平均敏感度为 75%，平均特异性为 89%，平均 AUC 为 0.58。
本研究是一个概念验证的人工智能系统，可以在糖尿病照片筛查途径中实施。性能有希望，但尚未达到临床应用所需的水平。我们已经表明，临床医生可以使用标准笔记本电脑，无需事先编程或人工智能知识来开发人工智能分类器。
